44c84983b4
- schema: expected_record unique key (site,waybill_no) -> (site,handover_no,waybill_no), so the same waybill can belong to multiple handover batches without being overwritten - store: dedup by (handover_no,waybill_no) instead of waybill_no alone; UPSERT conflict key matches the new unique key; handover_no no longer force-overwritten on conflict - store: add purge_expected, called on force re-download; deletes by business_date (download day, same source as task date) rather than batch_out_date, which is offset from the download day for sites like yunda where download day != outbound day - store/runtime: thread force + target_date through ingest_task / _persist_to_db / _site_undelivered_handler so force re-download purges then re-ingests in one tx - db_compare: undelivered_pieces now sums per-waybill shortfall (total - arrived) instead of expected_total - arrived_total, unaffected by unrelated/extra scans
87 lines
4.8 KiB
SQL
87 lines
4.8 KiB
SQL
-- =====================================================================
|
||
-- CQHXDB / 到货核销数据持久化 schema
|
||
-- 设计：统一核心表 + JSONB raw 兜底（保留站点原始全列，一字段不丢）
|
||
-- 幂等：业务唯一键 UPSERT，重复下载天然合并、零冗余
|
||
-- 表：expected_record（运单级）/ actual_record（扫描件级）
|
||
-- / undelivered_record（百世站点直供未到明细，子单级）
|
||
-- =====================================================================
|
||
|
||
-- 隔离到专用 schema（不污染 public）；表名无需再加前缀。
|
||
CREATE SCHEMA IF NOT EXISTS inbound_verify;
|
||
SET search_path TO inbound_verify;
|
||
|
||
-- 应到货物（运单级：一运单一批次一行；同运单可跨批次，按 交接单号+运单号 去重后入库）
|
||
CREATE TABLE IF NOT EXISTS expected_record (
|
||
id BIGSERIAL PRIMARY KEY,
|
||
site TEXT NOT NULL, -- 站点：顺心 / 中通 / 韵达 / 安能
|
||
waybill_no TEXT NOT NULL, -- 运单基号
|
||
handover_no TEXT, -- 交接单号
|
||
handover_pieces INTEGER, -- 交接件数（应到件数口径）
|
||
order_pieces INTEGER, -- 录单件数
|
||
business_date DATE, -- 业务日期（属性，非唯一键；读不到则 NULL）
|
||
out_date DATE, -- 出库日（批次归属日口径；从 raw.出库时间 解析）
|
||
batch_out_date DATE, -- 批次归属日（同交接单号出库日众数，并列取较早）
|
||
raw JSONB NOT NULL, -- 站点原始全列（key=原列名）
|
||
ingested_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||
UNIQUE (site, handover_no, waybill_no)
|
||
);
|
||
-- 迁移：旧唯一键 (site, waybill_no) → 新 (site, handover_no, waybill_no)。
|
||
-- CREATE TABLE IF NOT EXISTS 不改已存在的表，故用幂等 ALTER 切换约束。
|
||
ALTER TABLE expected_record DROP CONSTRAINT IF EXISTS expected_record_site_waybill_no_key;
|
||
DO $$
|
||
BEGIN
|
||
IF NOT EXISTS (
|
||
SELECT 1 FROM pg_constraint
|
||
WHERE conname = 'expected_record_site_handover_waybill_key'
|
||
) THEN
|
||
ALTER TABLE expected_record
|
||
ADD CONSTRAINT expected_record_site_handover_waybill_key
|
||
UNIQUE (site, handover_no, waybill_no);
|
||
END IF;
|
||
END $$;
|
||
CREATE INDEX IF NOT EXISTS idx_expected_site_date ON expected_record (site, business_date);
|
||
CREATE INDEX IF NOT EXISTS idx_expected_handover ON expected_record (site, handover_no);
|
||
CREATE INDEX IF NOT EXISTS idx_expected_out_date ON expected_record (site, out_date);
|
||
CREATE INDEX IF NOT EXISTS idx_expected_batch_out_date ON expected_record (site, batch_out_date);
|
||
|
||
-- 实到货物（扫描件级：一扫描一行；每扫描一件系统生成一个单号）
|
||
CREATE TABLE IF NOT EXISTS actual_record (
|
||
id BIGSERIAL PRIMARY KEY,
|
||
site TEXT NOT NULL,
|
||
waybill_no TEXT NOT NULL, -- 运单基号（由扫描单号推导）
|
||
piece_no TEXT NOT NULL, -- 扫描单号 / 子单号（业务唯一键）
|
||
scan_time TIMESTAMPTZ, -- 扫描时间（尽力解析，失败存 NULL，原始值在 raw）
|
||
scan_site TEXT, -- 扫描网点
|
||
raw JSONB NOT NULL,
|
||
ingested_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||
UNIQUE (site, piece_no)
|
||
);
|
||
CREATE INDEX IF NOT EXISTS idx_actual_waybill ON actual_record (site, waybill_no);
|
||
CREATE INDEX IF NOT EXISTS idx_actual_scan_time ON actual_record (scan_time);
|
||
|
||
-- 应到未到（百世站点直供未到明细：子单级）
|
||
CREATE TABLE IF NOT EXISTS undelivered_record (
|
||
id BIGSERIAL PRIMARY KEY,
|
||
site TEXT NOT NULL, -- 百世
|
||
waybill_no TEXT, -- 运单号
|
||
piece_no TEXT, -- 子单号（业务唯一键）
|
||
biz_type TEXT, -- 类型
|
||
last_scan TEXT, -- 最新扫描记录
|
||
raw JSONB NOT NULL,
|
||
ingested_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||
UNIQUE (site, piece_no)
|
||
);
|
||
|
||
-- 百世日聚合（应扫/已扫基数：站级日聚合，区别于运单级/件级/子单级表）
|
||
CREATE TABLE IF NOT EXISTS baishi_daily_stats (
|
||
id BIGSERIAL PRIMARY KEY,
|
||
site TEXT NOT NULL, -- 百世
|
||
business_date DATE NOT NULL, -- 业务日期（百世固定当天）
|
||
expected_pieces INTEGER, -- 应扫（应到基数）
|
||
arrived_pieces INTEGER, -- 已扫（实到基数）
|
||
undelivered_pieces INTEGER, -- 未扫（=应扫-已扫，任一缺失则 NULL）
|
||
raw JSONB NOT NULL, -- 原始抓取值
|
||
ingested_at TIMESTAMPTZ NOT NULL DEFAULT now(),
|
||
UNIQUE (site, business_date)
|
||
);
|